Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 411 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1291436 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5500. Min Act: -0.0000

Data Index: 951585 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1993 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5244. Min Act: -0.0000

Data Index: 825742 (The Pile)

Max Activating Token Index: 602

Text #4

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1643533 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1719194 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4901. Min Act: -0.0000

Data Index: 358122 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5025. Min Act: -0.0000

Data Index: 896565 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5038. Min Act: -0.0000

Data Index: 704515 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1164710 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1456499 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4779. Min Act: -0.0000

Data Index: 850448 (The Pile)

Max Activating Token Index: 551

Text #12

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5063. Min Act: -0.0000

Data Index: 229149 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5132. Min Act: -0.0000

Data Index: 226275 (The Pile)

Max Activating Token Index: 248

Text #14

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1425210 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1702030 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1051551 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1407812 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4829. Min Act: -0.0000

Data Index: 334754 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4378. Min Act: -0.0000

Data Index: 336529 (The Pile)

Max Activating Token Index: 517